© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2705
    Prev
    Next
    INDEX
    Explanations

    conditions for positive outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    1.96
    ly
    1.80
    ्स
    1.77
    nya
    1.57
    shire
    1.53
    sd
    1.48
    ting
    1.48
    了
    1.44
    sman
    1.43
    ton
    1.41
    POSITIVE LOGITS
    UTHERN
    1.40
     meiosis
    1.39
     nicer
    1.39
     Cinque
    1.37
     strung
    1.36
     narcissistic
    1.35
     NICE
    1.32
     penta
    1.31
    साइटी
    1.31
    aking
    1.30
    Activations Density 0.101%

    No Known Activations